= Block-Seminar "Machine Learning for Computer Vision" =

=== Language ===

English 

=== Termine und Informationen ===

||'''Erster Termin für Themenvergabe'''||Mittwoch, 21.10.2009, 11-13 Uhr, Raum FR 6046 ||
||'''Weitere Termine und Raum'''|| Nach Absprache ||
||'''verantwortlich'''|| [[http://ml.cs.tu-berlin.de/en/klaus/index.html|Prof. Dr. Klaus-Robert Müller]] ||
||'''Ansprechtpartner(in)'''|| [[mailto:motoaki.kawanabe@first.fraunhofer.de|Motoaki Kawanabe, Ph.D Universität Tokio]] ||
||'''Sprechzeiten'''||nach Vereinbarung||

=== Themen ===

Das Blockseminar wird Artikel der Machine Learning Methoden fuer die Aufgaben in Computer Vision besprechen.

 * image representations including higher-order features and attributes
 * object and scene categorization
 * object detection and localization
 * image segmentation
 * large margin classifiers including multiple kernel learning
 * conditional random fields and topic models
 * learning (with) taxonomies
 * active learning and user feedback 

=== Paper Assignments ===

|| '''Student''' || '''Paper''' || '''Topic''' ||
|| Moritz || Blaschko&Lampert (ECCV2008)|| Object Detection ||



=== Literatur und Links ===


'''object and scene categorization'''

G. Csurka, C. Bray, C. Dance, and L. Fan, “Visual categorization with 
bags of keypoints,”in Workshop on Statistical Learning in Computer 
Vision, ECCV, Prague, Czech Republic, May 2004, pp. 1–22.
<<BR>>
http://www.cs.utexas.edu/~grauman/courses/spring2007/395T/papers/csurka_dance_bags_keypoints.pdf
<<BR>>
Betreuer: NN

S. Lazebnik, C. Schmid, and J. Ponce, “Beyond bags of features: 
Spatial pyramid matching for recognizing natural scene categories,” in 
IEEE Computer Society Conference on Computer Vision and Pattern 
Recognition, vol. 2, New York, USA, June 2006, pp. 2169–2178.
<<BR>>
http://people.cs.ubc.ca/~lowe/525/lazebnik06.pdf
<<BR>>
Betreuer: NN

M. Varma and D. Ray, “Learning the discriminative power-invariance 
trade-off,” in Proceedings of the IEEE 11th International Conference 
on Computer Vision (ICCV ’07), 2007, pp. 1–8.
<<BR>>
http://dx.doi.org/10.1109/ICCV.2007.4408875
<<BR>>
Betreuer: NN

P. Gehler and S. Nowozin, "On Feature Combination for Multiclass Object Classification",
ICCV 2009.
<<BR>>
ftp://ftp.vision.ee.ethz.ch/publications/proceedings/eth_biwi_00649.pdf
<<BR>>
Betreuer: NN

'''image representations including higher-order features and attributes'''

D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", IJCV 2004.
<<BR>>
http://people.cs.ubc.ca/~lowe/papers/ijcv04.pdf
<<BR>>
Betreuer: NN

Moosmann, Triggs and Jurie,
"Fast Discriminative Visual Codebooks using Randomized Clustering Forests", 
NIPS 2006.
<<BR>>
http://books.nips.cc/papers/files/nips19/NIPS2006_0741.pdf
<<BR>>
Betreuer: NN

Wei Zhang, Akshat Surve, Xiaoli Fern and Thomas Dietterich,
"Learning Non-Redundant Codebooks for Classifying Complex Objects",
ICML 2009.
<<BR>>
http://www.cs.mcgill.ca/~icml2009/papers/525.pdf
<<BR>>
Betreuer: NN

'''object detection and localization'''

P. Viola and M. Jones,
"Rapid Object Detection using a Boosted Cascade of Simple Features",
2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'01), vol.1, pp. 511, 2001.
<<BR>>
http://www.robots.ox.ac.uk/~cvrg/trinity2002/CVPR-2001.pdf
<<BR>>
Betreuer: NN

M. B. Blaschko and C. H. Lampert, "Learning to Localize Objects with Structured Output Regression", 
Computer Vision: ECCV 2008, 2-15.
<<BR>>
http://www.kyb.mpg.de/publications/attachments/ECCV2008-Blaschko_5247%5B0%5D.pdf
<<BR>>
Betreuer: NN

Torralba, A., Murphy, K. and Freeman, W.,
"Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection", CVPR 2004
<<BR>>
http://people.cs.ubc.ca/~murphyk/Papers/jointBoostCVPR04_camera.pdf
<<BR>>
Betreuer: NN

Pedro F. Felzenszwalb, Ross B. Girshick, David !McAllester and Deva Ramanan, 
"Object Detection with Discriminatively Trained Part Based Models", PAMI 2009.
<<BR>>
http://people.cs.uchicago.edu/~rbg/papers/Object-Detection-with-Discriminatively-Trained-Part-Based-Models--Felzenszwalb-Girshick-McAllester-Ramanan.pdf
<<BR>>
Betreuer: NN

'''image segmentation'''

J. Shi and J. Malik,
"Normalized Cuts and Image Segmentation",
IEEE Transactions on Pattern Analysis and Machine Intel ligence, 22(8):888–905, August 2000.
<<BR>>
http://people.csail.mit.edu/torralba/courses/6.870/papers/shi00.pdf
<<BR>>
Betreuer: NN

A. Kannan, J. Winn, and C. Rother,
"Clustering appearance and shape by learning jigsaws",
NIPS 2006.
<<BR>>
http://books.nips.cc/papers/files/nips19/NIPS2006_0909.pdf
<<BR>>
Betreuer: NN

'''large margin classifiers including multiple kernel learning'''

G. R. G. Lanckriet, N. Cristianini, P. Bartlett, L. El Ghaoui, and M. I. Jordan,
"Learning the kernel matrix with semidefinite programming", JMLR, 5:27–72, 2004.
<<BR>>
http://jmlr.csail.mit.edu/papers/volume5/lanckriet04a/lanckriet04a.pdf
<<BR>>
Betreuer: NN

S Andrews, I Tsochantaridis, T Hofmann,
"Support vector machines for multiple-instance learning",
NIPS 2003.
<<BR>>
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.8281&rep=rep1&type=pdf
<<BR>>
Betreuer: NN

multi-task/transfer?

'''conditional random fields and topic models'''

X. He, R. S. Zemel and M. A. Carreira-Perpinan, CVPR 2004.
"Multiscale Conditional Random Fields for Image Labeling",
<<BR>>
http://www.cs.utexas.edu/~grauman/courses/spring2007/395T/papers/he_zemel_multiscale_crfs_cvpr04.pdf
<<BR>>
Betreuer: NN

A.Bosch, A.Zisserman, X.Muñoz. Scene classification using a hybrid generative/discriminative approach. IEEE Transactions on Pattern Analysis and Machine Intelligence. vol. 30, Issue 4, pp.712-727, April 2008. 
<<BR>>
http://eia.udg.es/~aboschr/Publicacions/pami.pdf
<<BR>>
Betreuer: NN

L. Cao and L. Fei-Fei, “Spatially coherent latent topic model for concurrent object segmentation and classification,” in Proceedings of the 11th IEEE International Conference on Computer Vision (ICCV '07), 
Rio de Janeiro, Brazil, October 2007.
<<BR>>
http://vision.cs.princeton.edu/documents/CaoFei-Fei_ICCV2007.pdf
<<BR>>
Betreuer: NN

J Winn and J Shotton,
"The Layout Consistent Random Field for Recognizing and Segmenting Partially 
Occluded Objects", CVPR 2006.
<<BR>>
ftp://mi.eng.cam.ac.uk/pub/reports/shotton_cvpr06.pdf
<<BR>>
Betreuer: NN

J Reynolds and K Murphy,
"Figure-ground segmentation using a hierarchical conditional random field",
Computer and Robot Vision, CRV 2007.
<<BR>>
http://people.cs.ubc.ca/~murphyk/Papers/reynoldsCRV07.pdf
<<BR>>
Betreuer: NN

'''learning (with) taxonomies'''

Griffin, G., Perona, P., "Learning and using taxonomies for fast visual categoriza- 
tion", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 
2008.
<<BR>>
http://www.cs.ualberta.ca/~jag/papersVis2/08cvpr/data/papers/070.pdf
<<BR>>
Betreuer: NN

'''active learning and user feedback'''

'''other topics'''          

Derek Hoiem, Alexei A. Efros, Martial Hebert,
"Putting Objects in Perspective", Int J Comput Vis (2008) 80: 3–15.
<<BR>>
http://www.cs.cmu.edu/~efros/hoiem_ijcv2008.pdf
<<BR>>
Betreuer: NN

A Saxena, SH Chung, AY Ng,
"3-D Depth Reconstruction from a Single Still Image",
Int J Comput Vis (2008) 76: 53–69.
<<BR>>
http://www-cs.stanford.edu/people/asaxena/learningdepth/saxena_ijcv07_learningdepth.pdf
<<BR>>
Betreuer: NN